[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7885FPANSS4E4KHB7SJDXCX":3,"skill-same:01M7885FPANSS4E4KHB7SJDXCX":46},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":25,"commitSha":26,"skillDirectory":27,"forksCount":28,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":31,"ownerDescription":6,"updatedAt":32,"install":33,"resources":45},"01M7885FPANSS4E4KHB7SJDXCX","which-skill",null,"Pick the skill or flow that fits your situation. A router over the skills in this repo.","officialunofficial\u002Fskills","officialunofficial","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F127067914?v=4","01M78827JABEMMN63AC8J1RCXV","Official Unofficial, Inc.","01M78827KC164SFKN4DXTCKK7N",7,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fofficialunofficial\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fengineering\u002Fwhich-skill\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: which-skill\ndescription: Pick the skill or flow that fits your situation. A router over the skills in this repo.\ndisable-model-invocation: true\n---\n\n# Which skill?\n\nYou won't hold every skill in your head, so route through this instead of guessing.\n\nA **flow** is a path traced across the skills. Most work follows a single **main flow**, with two **on-ramps** feeding into it. The rest are either standalone tools or a vocabulary layer that operates beneath everything else.\n\n## The main flow: idea → ship\n\nThe route most work takes. You have an idea; you want it built.\n\n1. **`\u002Fgrill-with-docs`** — sharpen the idea through interview. Start here when there **is a codebase**: it keeps state, folding what it learns back into `CONTEXT.md` and ADRs. (No codebase yet? Use `\u002Fgrill-me` — see Standalone. Both drive the same `\u002Fgrilling` primitive; only `grill-with-docs` leaves a written trail.)\n2. **Branch — can every open question be closed in conversation?** If any question demands a runnable answer (state, business logic, a UI you have to lay eyes on), take a detour through a prototype, with **`\u002Fhandoff`** carrying context in each direction (see Crossing sessions):\n   - **`\u002Fhandoff`** out, then start a clean session against that file,\n   - **`\u002Fprototype`** to settle the question with disposable code,\n   - **`\u002Fhandoff`** the findings back, and cite them from the original idea thread.\n3. **Branch — do you know what the feature actually rests on?** If it's unclear which capabilities the idea needs versus what the codebase already provides, run **`\u002Fto-primitives`**: it grades every capability against HEAD (`exists` \u002F `partial` \u002F `missing`, cited) and leaves a design doc with a build-order graph that `\u002Fto-prd` and `\u002Fto-issues` can draw on. Skip it when the ground is already obvious.\n4. **Branch — is this a multi-session build?**\n   - **Yes** → **`\u002Fto-prd`** (fold the thread into a PRD) → **`\u002Fto-issues`** (cut the PRD into issues anyone can grab independently). Since the issues stand alone, **reset context between them**: open a fresh session per issue and start **`\u002Fimplement`** with the PRD plus the one issue to work on.\n   - **No** → **`\u002Fimplement`** right here, without leaving this context window.\n\n   Either path, **`\u002Fimplement`** delivers each issue by driving **`\u002Ftdd`** underneath — one red-green slice at a time — then finishes with **`\u002Fcode-review`**, a two-axis pass (Standards + Spec) over the diff, before it commits. Pull in **`\u002Ftdd`** by itself when you simply want a concrete behaviour built test-first without a full spec, and **`\u002Fcode-review`** by itself whenever you want a branch or PR checked against a fixed baseline.\n\n### Context hygiene\n\nHold steps 1–4 inside **one continuous context window** — don't compact or clear until `\u002Fto-issues` is done — so the grilling, the PRD, and the issues all rest on the same line of thinking. Each `\u002Fimplement` then begins clean, taking the issue as its starting point.\n\nWhat bounds this is the **smart zone**: the window (roughly 120k tokens on current frontier models) inside which the model still reasons crisply. If a session nears that edge before `\u002Fto-issues`, don't grind on through degraded reasoning — `\u002Fhandoff` and pick up in a fresh thread.\n\n## On-ramps\n\nA starting situation that generates work, then merges onto the main flow.\n\n- **Bugs and requests stacking up** → **`\u002Ftriage`**. It walks issues through their triage roles and turns out agent-ready issues, which **`\u002Fimplement`** later collects.\n\n  Triage is for issues **you didn't author** — bug reports, incoming feature requests, whatever lands raw. Issues that `\u002Fto-issues` produced are already agent-ready, so **skip triage for those**.\n\n- **Backlog gone stale** → **`\u002Faudit-issue`**. Point it at an old issue or epic and it verifies every claim against HEAD, teaches back what the tree affords, and recommends keep \u002F rescope \u002F close — with drafted closing comments so the research survives the closure. Issues it recommends rescoping feed `\u002Fto-issues`; ones worth keeping feed `\u002Fimplement`.\n\n- **Something's broken** → **`\u002Fdiagnosing-bugs`**. Built for the stubborn ones: the bug that shrugs off a first look, the intermittent flake, the regression that slipped in between two known-good points. It won't theorise until it holds a **tight feedback loop** — one command that already goes red on *this* bug — then lands the fix behind a regression test. Its post-mortem hands off to **`\u002Fimprove-codebase-architecture`** when the real lesson is that no clean seam exists to pin the bug down.\n\n## Loops\n\nRecurring work, or the main flow with nobody watching in real time.\n\n- **`\u002Fdesigning-loops`** — reference for the four loop shapes and how to write a completion criterion that actually stops the loop. Read this before wiring up any of the below.\n- **`\u002Fdependency-update-loop`**, **`\u002Fstacked-pr-loop`**, **`\u002Fdeploy-verify-loop`** — ready-to-hand-to-a-schedule recipes for the recurring maintenance that piles up around shipped code: bot PRs, PR stacks, and the window right after a deploy.\n\n## Codebase health\n\nNot feature work — upkeep.\n\n- **`\u002Fimprove-codebase-architecture`** — reach for it whenever you have a spare moment to keep the codebase pleasant for agents to work in. It surfaces **deepening opportunities**; choosing one _spawns an idea_ you can carry into the main flow at `\u002Fgrill-with-docs`. It's the survey that turns up candidates; **`\u002Fcodebase-design`** (below) is the bench where you shape the one you picked.\n\n## Verification\n\nTurn a spec or a settled design into the checks that keep an implementation honest. Each distils the current thread into an in-repo doc; run them once the design is firm, before or alongside `\u002Fimplement`. They compound — invariants become fuzz oracles, and both sharpen the conformance suite.\n\n- **`\u002Fto-invariants`** — the properties that must *always* hold. Splits into design-level system invariants and enforceable ones, each mapped to a check or flagged as an unguarded **GAP**. Start here; the other two lean on its output.\n- **`\u002Fto-fuzz`** — the targets worth fuzzing, each pinned to an **oracle** (differential, round-trip, invariant, crash). Reuses `\u002Fto-invariants` output directly — every enforceable invariant is a ready-made oracle.\n- **`\u002Fto-conformance`** — a spec's normative requirements (MUST\u002FSHOULD\u002FMAY) turned into implementation-independent tests any conforming build must pass, with a traceability matrix and flagged spec ambiguities.\n\n## Vocabulary underneath\n\nTwo model-invoked references that sit *below* the other skills — each the single source of truth for its vocabulary. Call them directly when the **words**, not the process, are the sticking point; or let the skills above draw them in.\n\n- **`\u002Fdomain-modeling`** — tighten the project's *domain* language: challenge a fuzzy term, untangle an overloaded word (\"account\" pulling triple duty), pin a hard-to-reverse decision into an ADR. It's the live discipline `\u002Fgrill-with-docs` drives to keep `CONTEXT.md` a clean glossary.\n- **`\u002Fcodebase-design`** — the deep-module vocabulary (module, interface, depth, seam, adapter, leverage, locality) for shaping a module's *form*: plenty of behaviour behind a small interface at a clean seam. Both `\u002Ftdd` and `\u002Fimprove-codebase-architecture` speak it.\n\n## Crossing sessions\n\n- **`\u002Fhandoff`** — when a thread is full or you need to peel off (say, into a `\u002Fprototype` session), this compresses the conversation into a markdown file. You don't resume in place — you **open a new session and point it at that file** to ferry the context across. It's the bridge between context windows, working either way. Use it when you want a **fresh session** but need the **current conversation kept intact**.\n- **`\u002Fcompact`** (built-in) — stay in the **same conversation** and let the earlier turns be summarized. Use it at **deliberate breaks between phases**, when losing the verbatim history is fine. Don't compact mid-phase — the agent can lose the thread. `\u002Fhandoff` forks; `\u002Fcompact` continues.\n\n## Standalone\n\nOff the main flow entirely.\n\n- **`\u002Fgrill-me`** — the same unrelenting interview as `\u002Fgrill-with-docs`, but for when there's **no codebase**. Stateless: it writes nothing locally, builds no `CONTEXT.md`. Reach for it to sharpen any plan or design that doesn't live in a repo.\n- **`\u002Fprototype`** — a small, disposable program that answers one design question: does this state model feel right, or what should this UI look like. Throwaway from the first line — keep the answer, delete the code. It's the detour in step 2 of the main flow, but reach for it any time a design question is hard to settle on paper.\n- **`\u002Fresearch`** — hand the reading legwork to a **background agent**: it chases a question through **primary sources**, then drops a cited Markdown file into the repo. Keep working while it reads. What it produces is something to bring *into* the main flow at `\u002Fgrill-with-docs` — research feeds the thinking, it doesn't stand in for it.\n- **`\u002Fteach`** — learn a concept across several sessions, treating the current directory as a stateful workspace.\n- **`\u002Fwriting-great-skills`** — reference for writing and editing skills well.\n\n## Precondition\n\n**`\u002Fsetup-skills`** — run it before your first engineering flow to configure the issue tracker, triage labels, and doc layout the other skills expect. Custom issue trackers work too.\n","# Which skill?\n\nYou won't hold every skill in your head, so route through this instead of guessing.\n\nA **flow** is a path traced across the skills. Most work follows a single **main flow**, with two **on-ramps** feeding into it. The rest are either standalone tools or a vocabulary layer that operates beneath everything else.\n\n## The main flow: idea → ship\n\nThe route most work takes. You have an idea; you want it built.\n\n1. **`\u002Fgrill-with-docs`** — sharpen the idea through interview. Start here when there **is a codebase**: it keeps state, folding what it learns back into `CONTEXT.md` and ADRs. (No codebase yet? Use `\u002Fgrill-me` — see Standalone. Both drive the same `\u002Fgrilling` primitive; only `grill-with-docs` leaves a written trail.)\n2. **Branch — can every open question be closed in conversation?** If any question demands a runnable answer (state, business logic, a UI you have to lay eyes on), take a detour through a prototype, with **`\u002Fhandoff`** carrying context in each direction (see Crossing sessions):\n   - **`\u002Fhandoff`** out, then start a clean session against that file,\n   - **`\u002Fprototype`** to settle the question with disposable code,\n   - **`\u002Fhandoff`** the findings back, and cite them from the original idea thread.\n3. **Branch — do you know what the feature actually rests on?** If it's unclear which capabilities the idea needs versus what the codebase already provides, run **`\u002Fto-primitives`**: it grades every capability against HEAD (`exists` \u002F `partial` \u002F `missing`, cited) and leaves a design doc with a build-order graph that `\u002Fto-prd` and `\u002Fto-issues` can draw on. Skip it when the ground is already obvious.\n4. **Branch — is this a multi-session build?**\n   - **Yes** → **`\u002Fto-prd`** (fold the thread into a PRD) → **`\u002Fto-issues`** (cut the PRD into issues anyone can grab independently). Since the issues stand alone, **reset context between them**: open a fresh session per issue and start **`\u002Fimplement`** with the PRD plus the one issue to work on.\n   - **No** → **`\u002Fimplement`** right here, without leaving this context window.\n\n   Either path, **`\u002Fimplement`** delivers each issue by driving **`\u002Ftdd`** underneath — one red-green slice at a time — then finishes with **`\u002Fcode-review`**, a two-axis pass (Standards + Spec) over the diff, before it commits. Pull in **`\u002Ftdd`** by itself when you simply want a concrete behaviour built test-first without a full spec, and **`\u002Fcode-review`** by itself whenever you want a branch or PR checked against a fixed baseline.\n\n### Context hygiene\n\nHold steps 1–4 inside **one continuous context window** — don't compact or clear until `\u002Fto-issues` is done — so the grilling, the PRD, and the issues all rest on the same line of thinking. Each `\u002Fimplement` then begins clean, taking the issue as its starting point.\n\nWhat bounds this is the **smart zone**: the window (roughly 120k tokens on current frontier models) inside which the model still reasons crisply. If a session nears that edge before `\u002Fto-issues`, don't grind on through degraded reasoning — `\u002Fhandoff` and pick up in a fresh thread.\n\n## On-ramps\n\nA starting situation that generates work, then merges onto the main flow.\n\n- **Bugs and requests stacking up** → **`\u002Ftriage`**. It walks issues through their triage roles and turns out agent-ready issues, which **`\u002Fimplement`** later collects.\n\n  Triage is for issues **you didn't author** — bug reports, incoming feature requests, whatever lands raw. Issues that `\u002Fto-issues` produced are already agent-ready, so **skip triage for those**.\n\n- **Backlog gone stale** → **`\u002Faudit-issue`**. Point it at an old issue or epic and it verifies every claim against HEAD, teaches back what the tree affords, and recommends keep \u002F rescope \u002F close — with drafted closing comments so the research survives the closure. Issues it recommends rescoping feed `\u002Fto-issues`; ones worth keeping feed `\u002Fimplement`.\n\n- **Something's broken** → **`\u002Fdiagnosing-bugs`**. Built for the stubborn ones: the bug that shrugs off a first look, the intermittent flake, the regression that slipped in between two known-good points. It won't theorise until it holds a **tight feedback loop** — one command that already goes red on *this* bug — then lands the fix behind a regression test. Its post-mortem hands off to **`\u002Fimprove-codebase-architecture`** when the real lesson is that no clean seam exists to pin the bug down.\n\n## Loops\n\nRecurring work, or the main flow with nobody watching in real time.\n\n- **`\u002Fdesigning-loops`** — reference for the four loop shapes and how to write a completion criterion that actually stops the loop. Read this before wiring up any of the below.\n- **`\u002Fdependency-update-loop`**, **`\u002Fstacked-pr-loop`**, **`\u002Fdeploy-verify-loop`** — ready-to-hand-to-a-schedule recipes for the recurring maintenance that piles up around shipped code: bot PRs, PR stacks, and the window right after a deploy.\n\n## Codebase health\n\nNot feature work — upkeep.\n\n- **`\u002Fimprove-codebase-architecture`** — reach for it whenever you have a spare moment to keep the codebase pleasant for agents to work in. It surfaces **deepening opportunities**; choosing one _spawns an idea_ you can carry into the main flow at `\u002Fgrill-with-docs`. It's the survey that turns up candidates; **`\u002Fcodebase-design`** (below) is the bench where you shape the one you picked.\n\n## Verification\n\nTurn a spec or a settled design into the checks that keep an implementation honest. Each distils the current thread into an in-repo doc; run them once the design is firm, before or alongside `\u002Fimplement`. They compound — invariants become fuzz oracles, and both sharpen the conformance suite.\n\n- **`\u002Fto-invariants`** — the properties that must *always* hold. Splits into design-level system invariants and enforceable ones, each mapped to a check or flagged as an unguarded **GAP**. Start here; the other two lean on its output.\n- **`\u002Fto-fuzz`** — the targets worth fuzzing, each pinned to an **oracle** (differential, round-trip, invariant, crash). Reuses `\u002Fto-invariants` output directly — every enforceable invariant is a ready-made oracle.\n- **`\u002Fto-conformance`** — a spec's normative requirements (MUST\u002FSHOULD\u002FMAY) turned into implementation-independent tests any conforming build must pass, with a traceability matrix and flagged spec ambiguities.\n\n## Vocabulary underneath\n\nTwo model-invoked references that sit *below* the other skills — each the single source of truth for its vocabulary. Call them directly when the **words**, not the process, are the sticking point; or let the skills above draw them in.\n\n- **`\u002Fdomain-modeling`** — tighten the project's *domain* language: challenge a fuzzy term, untangle an overloaded word (\"account\" pulling triple duty), pin a hard-to-reverse decision into an ADR. It's the live discipline `\u002Fgrill-with-docs` drives to keep `CONTEXT.md` a clean glossary.\n- **`\u002Fcodebase-design`** — the deep-module vocabulary (module, interface, depth, seam, adapter, leverage, locality) for shaping a module's *form*: plenty of behaviour behind a small interface at a clean seam. Both `\u002Ftdd` and `\u002Fimprove-codebase-architecture` speak it.\n\n## Crossing sessions\n\n- **`\u002Fhandoff`** — when a thread is full or you need to peel off (say, into a `\u002Fprototype` session), this compresses the conversation into a markdown file. You don't resume in place — you **open a new session and point it at that file** to ferry the context across. It's the bridge between context windows, working either way. Use it when you want a **fresh session** but need the **current conversation kept intact**.\n- **`\u002Fcompact`** (built-in) — stay in the **same conversation** and let the earlier turns be summarized. Use it at **deliberate breaks between phases**, when losing the verbatim history is fine. Don't compact mid-phase — the agent can lose the thread. `\u002Fhandoff` forks; `\u002Fcompact` continues.\n\n## Standalone\n\nOff the main flow entirely.\n\n- **`\u002Fgrill-me`** — the same unrelenting interview as `\u002Fgrill-with-docs`, but for when there's **no codebase**. Stateless: it writes nothing locally, builds no `CONTEXT.md`. Reach for it to sharpen any plan or design that doesn't live in a repo.\n- **`\u002Fprototype`** — a small, disposable program that answers one design question: does this state model feel right, or what should this UI look like. Throwaway from the first line — keep the answer, delete the code. It's the detour in step 2 of the main flow, but reach for it any time a design question is hard to settle on paper.\n- **`\u002Fresearch`** — hand the reading legwork to a **background agent**: it chases a question through **primary sources**, then drops a cited Markdown file into the repo. Keep working while it reads. What it produces is something to bring *into* the main flow at `\u002Fgrill-with-docs` — research feeds the thinking, it doesn't stand in for it.\n- **`\u002Fteach`** — learn a concept across several sessions, treating the current directory as a stateful workspace.\n- **`\u002Fwriting-great-skills`** — reference for writing and editing skills well.\n\n## Precondition\n\n**`\u002Fsetup-skills`** — run it before your first engineering flow to configure the issue tracker, triage labels, and doc layout the other skills expect. Custom issue trackers work too.\n",{"name":5,"description":7,"disable-model-invocation":24},true,"main","e1e71e8aa302edca3e052370aefa9272f86d07ee","skills\u002Fengineering\u002Fwhich-skill",0,"https:\u002F\u002Fgithub.com\u002Fofficialunofficial\u002Fskills","https:\u002F\u002Fgithub.com\u002Fofficialunofficial","officialunofficial.com","2026-11-06 10:07:10",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":24},[35,38,41],{"tool":36,"command":37},"npx","npx skills add officialunofficial\u002Fskills --skill which-skill",{"tool":39,"command":40},"bunx","bunx skills add officialunofficial\u002Fskills --skill which-skill",{"tool":42,"command":43},"pnpm","pnpm dlx skills add officialunofficial\u002Fskills --skill which-skill","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fofficialunofficial\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fengineering\u002Fwhich-skill\u002FSKILL.md",[],[47,54,61,68,75,82],{"skillNo":48,"name":49,"nameZh":6,"description":50,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":51,"categories":52,"keywords":53,"publishedAt":19},"01M7887BDP2BC5HFHEKCNMBZ4Q","writing-great-skills","Reference for writing and editing skills well — the vocabulary and principles that make a skill predictable.","https:\u002F\u002Fgithub.com\u002Fofficialunofficial\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fproductivity\u002Fwriting-great-skills\u002FSKILL.md",[],[],{"skillNo":55,"name":56,"nameZh":6,"description":57,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"publishedAt":19},"01M788772K4QYXCZX3Y2P2AX9V","technical-writing","House style for technical writing — the voice, sentence craft, formatting, and user-facing-copy rules that make docs and product text clear, direct, and consistent. Use when writing or editing a README, docs, a spec, release notes, a changelog, help text, or any error\u002FCLI\u002FUI copy a person reads; when reviewing a diff that touches prose or messages; or when a project needs a writing standard. Reference-heavy mechanics live in REFERENCE.md.","https:\u002F\u002Fgithub.com\u002Fofficialunofficial\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fproductivity\u002Ftechnical-writing\u002FSKILL.md",[],[],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":19},"01M78875087F1XKP7C6VRC49CY","teach","Teach the user a new skill or concept, within this workspace.","https:\u002F\u002Fgithub.com\u002Fofficialunofficial\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fproductivity\u002Fteach\u002FSKILL.md",[],[],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":19},"01M78872Z38MACN22AQDY9410P","handoff","Compact the current conversation into a handoff document for another agent to pick up.","https:\u002F\u002Fgithub.com\u002Fofficialunofficial\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fproductivity\u002Fhandoff\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":19},"01M78870FVRDYRT1WVP9HJ6FQ3","grilling","Interrogate the user's plan or design one decision at a time until you both share the same understanding. Use when the user wants to pressure-test an idea before building it, or reaches for any 'grill' trigger phrase.","https:\u002F\u002Fgithub.com\u002Fofficialunofficial\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fproductivity\u002Fgrilling\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":19},"01M7886XGPEWXZYDA6K310HNYP","grill-me","A relentless, one-decision-at-a-time interview that sharpens a plan or design.","https:\u002F\u002Fgithub.com\u002Fofficialunofficial\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fproductivity\u002Fgrill-me\u002FSKILL.md",[],[]]